Many downstream NLP tasks have shown significant improvement through continual pre-training, transfer learning and multi-task learning. State-of-the-art approaches in Word Sense Disambiguation today benefit from some of these approaches in conjunction with information sources such as semantic relationships and gloss definitions contained within WordNet. Our work builds upon these systems and uses data augmentation along with extensive pre-training on various different NLP tasks and datasets. Our transfer learning and augmentation pipeline achieves state-of-the-art single model performance in WSD and is at par with the best ensemble results.

中文翻译：

---

转移学习和增强词义歧义

通过持续的预培训，迁移学习和多任务学习，许多下游NLP任务已显示出显着的改进。如今，词义歧义消除的最先进方法得益于其中一些方法与信息源的结合，例如WordNet中包含的语义关系和光泽定义。我们的工作建立在这些系统的基础上，并使用数据扩充以及对各种不同的NLP任务和数据集的广泛预培训。我们的转移学习和扩充管道在WSD中实现了最先进的单模型性能，并且与最佳合奏结果相当。